FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding

TL;DR

FMGS introduces an efficient 3D scene representation that combines foundation model embeddings with Gaussian splatting, achieving high-quality, fast, multi-view semantic understanding for augmented reality and robotics.

Contribution

This work is the first to embed vision-language foundation models into 3D Gaussian splatting, enabling efficient reconstruction and semantic consistency in 3D scene understanding.

Findings

Achieves 10.2% improvement in open-vocabulary object detection.

Runs 851 times faster for inference compared to previous methods.

Demonstrates high multi-view semantic consistency.

Abstract

Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present Foundation Model Embedded Gaussian Splatting (FMGS), which incorporates vision-language embeddings of foundation models into 3D Gaussian Splatting (GS). The key contribution of this work is an efficient method to reconstruct and represent 3D vision-language models. This is achieved by distilling feature maps generated from image-based foundation models into those rendered from our 3D model. To ensure high-quality rendering and fast training, we introduce a novel scene representation by integrating strengths from both GS and multi-resolution hash encodings (MHE). Our effective training procedure also introduces a pixel alignment loss that makes the rendered feature distance of the same semantic entities close, following the pixel-level semantic boundaries. Our results demonstrate remarkable multi-view semantic consistency, facilitating diverse downstream tasks, beating state-of-the-art methods by 10.2 percent on open-vocabulary language-based object detection, despite that we are 851X faster for inference. This research explores the intersection of vision, language, and 3D scene representation, paving the way for enhanced scene understanding in uncontrolled real-world environments. We plan to release the code on the project page.